User trust relationship prediction method and system based on graph self-encoding network

Abstract

The invention discloses a user trust relationship prediction method and system based on a graph self-encoding network, and the method comprises the steps: obtaining comment interaction data between users, and constructing a user trust relationship network; extracting an adjacency matrix based on the user trust relationship network, and converting the adjacency matrix into a directed activation propagation adjacency matrix; calculating a symbol network reachable matrix in combination with the symbol network activation propagation adjacency matrix, and performing recursion on a high-order symbolnetwork reachable matrix; taking the reachable matrix of the high-order symbol network as the input of a graph convolution network, and encoding the symbol network by using a spectral domain graph convolution method to obtain a network embedding result; and taking the network embedding result as a code of the symbol network, and performing similarity measurement between nodes in the network by using an inner product decoding mode to obtain a reconstructed symbol network adjacency matrix, namely a user trust relationship network link prediction result. According to the invention, the application of the graph convolution network in the symbol network is realized, and the accuracy of user trust relationship prediction is improved.

Description

technical field [0001] The invention belongs to the technical field of network link prediction, and in particular relates to a user trust relationship prediction method and system based on a graph self-encoding network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Networks can represent complex systems, so they have received extensive attention in many fields. Network representation requires keeping the original topology and semantic information of the network unchanged while learning the low-dimensional latent representation of nodes. For example, in the comment trust network, if each user can be represented by a multi-dimensional vector, the information expression of the user on the network can be quantified, so as to dig out the trust sub-network starting from the user, and through certain symbol propagation rules, In this way, th...

AI Technical Summary

Problems solved by technology

[0005] However, according to the inventor's understanding, since the current graph convolutional network (GCN) only supports undirected and unsigned networks, it cannot be directly applied to directed symbolic networks, that is, the original graph convolutional network uses the unsigned network Lapla The Sri Lankan matrix has excellent properties of positive semi-definite pairs, and the Fourier transform is applied to realize the convolution operation of spectrograms

However, the directed symbolic network does not have this excellent property, so it cannot learn the negative relationship in the symbolic network, resulting in a serious imbalance in the final embedding result, and cannot effectively create potential value for related fields.

That is, it is impossible to properly handle the negative connection relationship in the symbolic network. If the negative connection in the symbolic network is ignored and the symbolic network is treated as an unsigned network, satisfactory embedding results will not be obtained, let alone cannot carry out follow-up tasks: for example, the direction and sign of edges in directed symbolic networks cannot be effectively processed, the problem of symbol propagation in symbolic networks cannot be solved, and the form of spectral domain convolution in directed symbolic networks cannot be realized, which limits Prediction accuracy

Images